2021 рік

Permanent URI for this community

https://ir.kneu.edu.ua/handle/2010/43381

Browse

Browsing 2021 рік by Subject "forecasting"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Forecasting electricity generation from renewable sources in developing countries (on the example of Ukraine)
    (ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Miroshnychenko, Ihor; Мірошниченко, Ігор Вікторович; Мирошниченко, Игорь Викторович; Kravchenko, Тetiana; Кравченко (Лук’янець), Тетяна Володимирівна; Лук’янець, Тетяна Володимирівна; Drobyna, Yuliia
    Electricity generation forecasting is a common task that helps power generating companies plan capacity, minimize costs, and detect anomaly. Despite its importance, there are serious challenges associated with obtaining reliable and high-quality forecasts, especially when it comes to the newly created renewable electricity market. A practical approach to predicting the generation of electricity from alternative sources in developing countries (on the example of Ukraine) based on the use of classical (ARIMA, TBATS) and modern (Prophet, NNAR) approaches is proposed. The legal framework regulating the process of Ukraine's entry into the pan-European energy market and its functioning was analyzed: the weak points of the legislation on responsibility, the permissible accuracy of weather conditions data, and the lack of data on the monitoring infrastructure are indicated. Among all the proposed alternatives, the Prophet model was the most accurate, since it allows you to simultaneously take into account several seasonalities (hourly, daily, weekly, monthly, and holidays). According to this, for an operational forecast (6 hours) the best model is the one that takes into account hourly seasonality, and for shortterm forecasts (24 and 48 hours) and medium-term forecast (72 hours) the most accurate models are those taking into account hourly, daily, weekly seasonality and weather conditions. The obtained forecasts and model quality indicators approve the feasibility of applying the proposed approach and the constructed models that can be used in a wide range of economic problems.
  • No Thumbnail Available
    Item
    Time series forecasting of agricultural product prices using Elman and Jordan recurrent neural networks
    (ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Kmytiuk, Tetiana; Majore, Ginta
    Most practical problems of forecasting time series are characterized by a high level of nonlinearity and nonstationarity, noise, the presence of irregular trends, jumps, and anomalous emissions. Under these conditions, statistical and mathematical assumptions limit the possibility of applying classical forecasting methods. The main disadvantage of statistical models is the difficulty of choosing the type of model and selecting its parameters. An alternative to these methods may be methods of computational intelligence, which include artificial neural networks, which can significantly improve the accuracy of time series prediction. A significant advantage of neural networks is that they are able to learn and generalize the accumulated knowledge, highlighting the hidden relationships between input and output data. At the moment, the most time series forecasting solutions based on this toolkit involve the use of feed-forward neural networks (perceptrons, convolutional neural networks, etc.). The article provides an overview of the architecture, principles of operation, and methods of teaching known models of recurrent neural networks. In the study, we built and compared the architectures of Elman and Jordan neural networks for solving the problem of forecasting prices for agricultural products. The corresponding statistical comparisons of the above models are also given. The experimental results show that such approach provides high accuracy in predicting the values from the price of agriculture products.